Combining Vision and Tactile Data for Cable Grasping

Caporali, Alessio; Galassi, Kevin; Laudante, Gianluca; Palli, Gianluca; Pirozzi, Salvatore

doi:10.1109/aim46487.2021.9517447

Cited by 7 publications

(6 citation statements)

References 16 publications

(17 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The peaks in the graph correspond to the moments when the sensor crosses the wire during the scanning and the mean value of these peaks is 31.8 mm. Moreover, in case the ẑ-coordinate was not precise enough, the tactile sensor could be exploited to apply a correction as shown in [3]. Figure 6 shows the grasping pose with the fingers aligned to the wire (6(a)), the position of the wire after the grasp (6(b)) and the respective tactile map with the estimated wire position read from the tactile sensors (6(c)).…”

Section: Grasping Experimentsmentioning

confidence: 99%

“…Figure 6 shows the grasping pose with the fingers aligned to the wire (6(a)), the position of the wire after the grasp (6(b)) and the respective tactile map with the estimated wire position read from the tactile sensors (6(c)). The algorithm used for the estimation of the wire position by using the tactile sensor is explained in [3].…”

Section: Grasping Experimentsmentioning

confidence: 99%

“…On the other side, tactile sensors are increasingly used for the manipulation tasks, as they allow complex control actions when the robot is in strict contact with an object [2], [3]. The starting point for grasping and manipulation should be the object pose estimated by the cameras.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Wire Grasping by Using Proximity and Tactile Sensors

Cirillo

Laudante

Pirozzi

2022

2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS)

Self Cite

View full text Add to dashboard Cite

Nowadays robots have to be able to perform increasingly complex tasks. In grasping and manipulation, the knowledge of the environment and the pose of the target object are crucial for the correct execution of the task. Vision systems are widely used for environment and object perception, but they need to be finely calibrated to obtain high accuracy and they are not able to sense small objects like thin wires. Tactile sensors could be used to explore areas close to the target object, but this "blind" physical interaction is not always feasible. This paper proposes a strategy to use a proximity sensor mounted on the robot's end effector to obtain a pose estimation of the target object that, in this study, is represented by a thin electrical wire.

show abstract

Section: Grasping Experimentsmentioning

confidence: 99%

Section: Grasping Experimentsmentioning

confidence: 99%

See 1 more Smart Citation

Wire Grasping by Using Proximity and Tactile Sensors

Cirillo

Laudante

Pirozzi

2022

2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS)

Self Cite

View full text Add to dashboard Cite

show abstract

“…This approach is better suited in case of occlusions and space limitation, and these sensors can provide important information in manipulation tasks [22]. Additionally, vision and tactile data can also be combined [23] to overcome the limitation of both solutions.…”

Section: Related Workmentioning

confidence: 99%

Cable Detection and Manipulation for DLO-in-Hole Assembly Tasks

Galassi

Caporali

Palli

2022

2022 IEEE 5th International Conference on Industrial Cyber-Physical Systems (ICPS)

View full text Add to dashboard Cite

This paper describes a cyber-physical system for the manipulation of Deformable Linear Objects (DLOs) addressing the DLO-in-hole insertion problem targeting an industrial scenario, the switchgear's components cabling task. In particular, the task considered is the insertion of DLOs in the switchgear components' holes. This task is very challenging since a precise knowledge of the DLO tip position and orientation is required for a successful operation. We tackled the DLO-in-hole problem from the computer vision perspective constraining our setup on employing just simple 2D images and by using the mobility of the robotic arm for achieving the full 3D knowledge of the DLOs. Then, the DLO tip is detected from two different image planes and the robot's trajectory corrected accordingly before insertion. To prove the effectiveness of the proposed solution, an example scenario is prepared and the method validated experimentally attempting the insertion of several DLOs in a sample switchgear component, obtaining an overall insertion success rate of 82.5%.

show abstract

“…Cable assembling is a challenge robotic manipulation task. Many significant progresses have been achieved in cable manipulation [15], cable insertion [16], and rearrangements [17]. Deformable object manipulation has been partially investigated by predicting robot actions through the utilization of visual data [18], [19].…”

Section: Related Work a Cable Graspingmentioning

confidence: 99%

Fine-grained Load Balancing with Traffic-aware Rerouting in DataCenter Networks

Zhang

Lei

Zhang

et al. 2021

Preprint

View full text Add to dashboard Cite

Modern datacenters provide a wide variety of application services, which generate a mix of delay-sensitive short flows and throughput-oriented long flows, transmitting in the multi-path datacenter network. Though the existing load balancing designs successfully make full use of available parallel paths and attain high bisection network bandwidth, they reroute flows regardless of their dissimilar performance requirements. The short flows suffer from the problems of large queuing delay and packet reordering, while the long flows fail to obtain high throughput due to low link utilization and packet reordering. To address these inefficiency, we design a fine-grained load balancing scheme, namely TR (Traffic-aware Rerouting), which identifies flow types and executes flexible and traffic-aware rerouting to balance the performances of both short and long flows. Besides, to avoid packet reordering, TR leverages the reverse ACKs to estimate the switch-to-switch delay, thus excluding paths that potentially cause packet reordering. Moreover, TR is only deployed on the switch without any modification on end-hosts. The experimental results of large-scale NS2 simulations show that TR reduces the average and tail flow completion time for short flows by up to 60% and 80%, as well as provides up to 3.02x gain in throughput of long flows compared to the state-of-the-art load balancing schemes.

show abstract

Combining Vision and Tactile Data for Cable Grasping

Cited by 7 publications

References 16 publications

Wire Grasping by Using Proximity and Tactile Sensors

Wire Grasping by Using Proximity and Tactile Sensors

Cable Detection and Manipulation for DLO-in-Hole Assembly Tasks

Fine-grained Load Balancing with Traffic-aware Rerouting in DataCenter Networks

Contact Info

Product

Resources

About